List processing method, computing device and storage medium

Abstract

The present invention discloses a list processing method, computing device, and storage medium, wherein the list processing method includes: collecting historical behavior data of users for books on a list to be processed; analyzing the behavior path depth of the historical behavior data to obtain the user's negative feedback level data for the books; and adjusting the order of the books in the list to be processed based on the negative feedback level data to obtain a processed list. According to the technical solution provided by the present invention, the user's negative feedback level data for the books is determined by analyzing the behavior path depth of the historical behavior data, and the order of the books in the list is adjusted based on the negative feedback level data, thereby achieving effective adjustment of the order of books that the user is not interested in, so that the order of the books in the list can be determined by integrating the user's preferences.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a list processing method, computing device, and storage medium. Background Art

[0002] Books in the form of e-books are loved by a large number of users due to their advantages such as ease of access. E-book platforms usually include a book list page, which recommends books to users through the book list page. Users' behaviors such as clicking and reading books can reflect their preferences for books to a certain extent. However, in the existing list processing method, books are usually arranged according to strategies such as book popularity and the number of book collectors to obtain the list. The user's preference for books based on behavior is not fed back into the list, resulting in the user seeing roughly the same books every time he browses the book list page. For example, the books that the user determined not to be interested in during the last browsing of the list will still be on the list the next time he browses the list. This list processing method cannot well integrate user preferences for book recommendations, resulting in poor book recommendation results. Summary of the Invention

[0003] In view of the above problems, the present invention is proposed to provide a list processing method, computing device and storage medium that overcome the above problems or at least partially solve the above problems.

[0004] According to one aspect of the present invention, a list processing method is provided, comprising:

[0005] Collect historical behavior data of users on books on the pending list;

[0006] Analyze the depth of the behavior path of historical behavior data to obtain the level of negative feedback from users on books;

[0007] According to the negative feedback level data, the order of the books in the list to be processed is adjusted to obtain the processed list.

[0008] According to another aspect of the present invention, there is provided a computing device comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0009] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:

[0010] Collect historical behavior data of users on books on the pending list;

[0011] Analyze the depth of the behavior path of historical behavior data to obtain the level of negative feedback from users on books;

[0012] According to the negative feedback level data, the order of the books in the list to be processed is adjusted to obtain the processed list.

[0013] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned list processing method.

[0014] According to the technical solution provided by the present invention, the user's historical behavior data on books is introduced into the list sorting mechanism, and the user's negative feedback level data on books is determined by analyzing the behavior path depth of the historical behavior data. The negative feedback level data can be used to reflect the degree of user's lack of interest in books. The order of books in the list is adjusted according to the negative feedback level data, so that the user's preference results for books are fed back to the list based on the user's behavior, thereby achieving effective adjustment of the order of books that the user is not interested in, making it possible to integrate the user's preferences to determine the order of books in the list, optimizing the book list processing method, and helping to obtain better book recommendation effects.

[0015] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0017] Figure 1 A flowchart of a list processing method according to the first embodiment of the present invention is shown;

[0018] Figure 2a A flowchart of a list processing method according to the second embodiment of the present invention is shown;

[0019] Figure 2b A schematic diagram showing a user's behavior path for books;

[0020] Figure 2c A schematic diagram showing the order of multiple books with the same book popularity value from front to back;

[0021] Figure 2d Shows the display of the book list page Figure 1 ;

[0022] Figure 2e Shows the second display diagram of the book list page;

[0023] Figure 3 A schematic structural diagram of a computing device according to a fourth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] Example 1

[0026] Figure 1 FIG. 1 shows a flowchart of a list processing method according to the first embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0027] Step S101: Collect historical behavior data of users on books in the list to be processed.

[0028] Among them, the pending list refers to a ranking list formed by arranging the books in the e-book platform in advance according to the initial sorting index of the list, and the pending list records the sorting order of multiple books. Taking into account that the user's click, reading and other behaviors on books can reflect their preferences for books to a certain extent, in this embodiment, the user's historical behavior data on books is introduced into the list sorting mechanism, and the user's historical behavior data is used to influence the sorting order of books in the pending list. Then, in step S101, it is necessary to collect the user's historical behavior data on the books in the pending list. The user's historical behavior data on the books in the pending list is data used to describe the interaction between the user and the book, and may specifically include: exposure book behavior data, click book behavior data, reading book behavior data, and adding to bookshelf behavior data, etc. The user's preference for books can be reflected through historical behavior data.

[0029] Step S102 : Analyze the behavior path depth of the historical behavior data to obtain the user's negative feedback level data on the book.

[0030] On the book list page, books are displayed in the order in which they are listed. Specifically, book information such as book covers, titles, and book descriptions for multiple books can be displayed. The user's behavioral path for the books displayed on the book list page mainly includes multiple nodes, such as exposure to the book, clicking on the book, entering the book details page, reading the book, and adding the book to the bookshelf. Specifically, users can browse book information such as book covers, titles, and book descriptions on the book list page. On the book list page, users can click on the book cover, title, or book description to enter the book details page to browse the book details. On the book details page, users can enter the book reading page to read the book by triggering the read button, etc. Users can also add books to their own bookshelf by triggering the add to bookshelf button, etc. To facilitate the determination of the user's negative feedback level data for books, multiple levels of feedback nodes can be set on the user's behavior path according to the depth of the behavior path. After collecting historical behavior data, the depth of the behavior path can be obtained by analyzing the historical behavior data, and the node data of the feedback node corresponding to the behavior path depth can be used as the negative feedback level data for the book.

[0031] Step S103: Adjust the order of the books in the to-be-processed list based on the negative feedback level data to obtain a processed list.

[0032] Among them, the negative feedback level data is data used to indicate the degree of user disinterest in a book. If a book has negative feedback level data, indicating that the user is not very interested in the book, then its recommendation weight can be reduced accordingly based on the negative feedback level data, so as to place the book further back in the order of the pending list, thereby obtaining a processed list. Specifically, the higher the level of negative feedback level data, the greater the degree of user disinterest in the book, and the greater the reduction in recommendation weight, and the further back the book is placed in the order of the pending list, thereby placing books that the user is not interested in at the back.

[0033] By utilizing the list processing method provided in this embodiment, the user's historical behavior data on books is introduced into the list sorting mechanism. By analyzing the behavioral path depth of the historical behavior data, the user's negative feedback level data on the books is determined. The negative feedback level data can be used to reflect the degree of user's lack of interest in the books. The order of the books in the list is adjusted according to the negative feedback level data, so that the user's preference results for the books are fed back to the list based on the user's behavior, thereby achieving effective adjustment of the order of the books that the user is not interested in, making it possible to integrate the user's preferences to determine the order of the books in the list, optimizing the book list processing method, and helping to obtain better book recommendation effects.

[0034] Example 2

[0035] Figure 2a FIG. 1 shows a flow chart of a list processing method according to the second embodiment of the present invention. Figure 2a As shown, the method includes the following steps:

[0036] Step S201: Collect historical behavior data of users on books in the list to be processed.

[0037] In this embodiment, considering that the user's historical behavior data for books on the pending list can reflect the user's preference for books, the user's historical behavior data for books is introduced into the list sorting mechanism, and the user's historical behavior data is used to influence the order of the books in the pending list. In step S201, the user's historical behavior data for the books on the pending list can be collected from the e-book platform, etc. The historical behavior data may include: exposure book behavior data, click book behavior data, reading book behavior data, and adding bookshelf behavior data. The historical behavior data may also include other data on the interaction between the user and the book, which is not limited here.

[0038] Step S202 : Setting multiple levels of feedback nodes on the user's behavior path for books according to the behavior path depth.

[0039] By analyzing the user's behavioral path for books, we can see that the behavioral path mainly includes: exposing books, clicking on books, entering the book details page, reading books, adding books to bookshelves and other nodes. Figure 2b A schematic diagram showing the user's behavior path for books is shown in FIG. Figure 2b As shown, the behavior path mainly includes: exposing the book information of the book to the user on the book list page; judging whether the user clicks on the book information, if clicked, entering the book details page, if not clicked, the user can return to the book list page, and the book information of other books is exposed to the user on the book list page; after entering the book details page, judging whether the user triggers the reading button, if triggered, entering the book reading page, if not triggered, the user can return to the book list page, and the book information of other books is exposed to the user on the book list page; after entering the book reading page, if the user finds that he likes this book through reading and wants to continue reading it later, he can add it to the bookshelf. If the user finds that he does not like this book through reading, he can return to the book list page, and the book information of other books is exposed to the user on the book list page.

[0040] From this behavior path, we can know that the user's preference for books can be predicted based on the user's operation behavior on the books in the pending list. If the user's operation behavior is "exposing books + clicking on books + reading books + adding to bookshelf", it can be determined that the user likes this book; conversely, if the user performs a series of operations of "exposing books", "clicking on books" and "reading books", but ultimately does not add the book to the bookshelf, it can be determined that the user is not interested in the book; because the more a user knows about a book, the higher the possibility of the decision he or she makes, then under the premise of not adding the book to the bookshelf, the more the above series of operations are performed, the higher the possibility of determining that the user is not interested in the book.

[0041] In step S202, the user's behavior path for books is analyzed to find nodes that can reflect the user's negative feedback, and multi-level feedback nodes are set on the behavior path according to the depth of the behavior path. Specifically, considering that the book is exposed but the user does not click on the book, the user clicks on the book but does not read it, and the book is read but not added to the bookshelf can all represent the user's negative feedback and can be used to reflect the degree of user disinterest in the book, then the set multi-level feedback nodes may include: feedback nodes corresponding to books that are exposed but not clicked on, feedback nodes corresponding to books that are clicked but not read, and feedback nodes corresponding to books that are read but not added to the bookshelf. Among them, since the more a user knows about a book, the higher the possibility of the decision he or she makes, then under the premise of not adding to the bookshelf, the deeper the depth of the behavior path, the higher the possibility of determining that the user is not interested in the book, and the higher the level of the corresponding feedback node. As Figure 2b As shown, the feedback node corresponding to exposing books but not clicking on them is a first-level feedback node, the feedback node corresponding to clicking on books but not reading them is a second-level feedback node, and the feedback node corresponding to reading books but not adding them to the bookshelf is a third-level feedback node. Among them, the level data of the three different levels of feedback nodes can be used to reflect the degree of user's lack of interest in books. The level of the third-level feedback node is higher than that of the second-level feedback node, and the level of the second-level feedback node is higher than that of the first-level feedback node.

[0042] Step S203 : Analyze the behavior path depth of the historical behavior data to obtain feedback nodes corresponding to the behavior path depth, and use the node data of the feedback nodes as the user's negative feedback level data for the book.

[0043] Specifically, the behavior path depth of the historical behavior data collected in step S201 is analyzed. If the analyzed behavior path depth has a corresponding feedback node, the node data of the feedback node is used as the negative feedback level data for the book. The node data of the feedback node may specifically include data such as the level of the feedback node and the behavior path depth corresponding to the feedback node. Those skilled in the art may also configure the node data to include other data, which is not limited here.

[0044] For example, a multi-level feedback node such as Figure 2b As shown, if the collected user's historical behavior data for book 1 in the list to be processed has a behavior path depth of exposing the book but not clicking on it, it corresponds to a first-level feedback node, and the node data of the first-level feedback node is used as the negative feedback level data of book 1. For example, the negative feedback level data of book 1 may include one level, and the corresponding behavior path depth is exposing the book but not clicking on it.

[0045] After obtaining the negative feedback level data, the order of the books in the list to be processed can be adjusted based on the negative feedback level data to obtain the processed list. If a book has negative feedback level data, it means that the user is not very interested in the book. Then, based on the negative feedback level data, its recommendation weight can be reduced accordingly to place the book in the order of the list to be processed further back. In actual application scenarios, the list to be processed refers to a ranking list formed by pre-arranging the books in the e-book platform according to the initial ranking index of the list. The list to be processed contains many books. For example, a list to be processed contains 300,000 books, and there will be many books under the same initial ranking index of the list. Then, under the same initial ranking index of the list, the order of the books in the list to be processed can be adjusted based on the negative feedback level data of these books. For books with different initial ranking indexes of the list, they are still sorted according to the preset order of the initial ranking index of the list. Specifically, this is achieved through steps S204 to S208.

[0046] Step S204: collecting the initial ranking index of each book in the list to be processed.

[0047] The initial ranking indicators include: book popularity, number of readers, number of likes, number of book collections, book ratings, update time, author follow-up parameters, and / or cumulative reading time. Author follow-up parameters can specifically include the number of fans of the author.

[0048] Step S205 , determining whether the initial ranking indexes of any two books in the list to be processed are the same; if so, executing step S206 ; if not, executing step S207 .

[0049] Step S206 , according to the negative feedback level data, lowering the recommendation weights of the books corresponding to the negative feedback level data, and adjusting the order of any two books in the to-be-processed list according to the recommendation weights.

[0050] When it is determined that the initial ranking indicators of any two books are the same, the recommendation weights of the books corresponding to the negative feedback level data are lowered according to the negative feedback level data, and the order of the two books in the list to be processed is adjusted according to the preset order of the recommendation weights, where the recommendation weight corresponds to the negative feedback level data, and the higher the level of the negative feedback level data, the lower the recommendation weight.

[0051] The following is an introduction to the book popularity value, which is the initial sorting indicator of the list. In the pending list, the books are generally sorted in order from high to low according to the book popularity value, where the book popularity value is usually in units of ten thousand. For multiple books with the same book popularity value, the recommendation weight of the book corresponding to the negative feedback level data is lowered, so that the higher the level of the negative feedback level data, the lower the recommendation weight of the corresponding book. In other words, for multiple books with the same book popularity value, among these multiple books, the recommendation weight of unexposed books is greater than the recommendation weight of books that are exposed but not clicked, the recommendation weight of books that are clicked but not read, and the recommendation weight of books that are read but not added to the bookshelf. The higher the recommendation weight, the higher the ranking of the corresponding book among the multiple books with the same book popularity value. Figure 2c A schematic diagram showing the order of multiple books with the same book popularity value from front to back is shown, Figure 2c As shown, among multiple books with the same book popularity value, the unexposed books are arranged at the front, the exposed but not clicked books are arranged behind the unexposed books, the clicked but not read books are arranged behind the exposed but not clicked books, and the books that are read but not added to the bookshelf are arranged behind the clicked but not read books.

[0052] Step S207: Determine the order of any two books in the list to be processed according to the preset order of the initial sorting indicators of the list.

[0053] The preset order can be from high to low or from low to high. Taking the initial sorting indicator of the list as the book popularity value and the preset order as from high to low as an example, assuming that the two books are book 1 and book 2, the user has negative feedback level data for book 1 and no negative feedback level data for book 2, but because the book popularity value of book 1 is higher than the book popularity value of book 2, the order of book 1 in the list to be processed is before the order of book 2, that is, book 1 is ranked before book 2.

[0054] Step S208: Obtain the processed list.

[0055] After completing the above sorting for all books in the list to be processed, the processed list can be obtained.

[0056] Step S209: adding behavior tags to the books based on the historical behavior data.

[0057] To help users quickly identify which books on the book list page they have read but not added to their bookshelf, and which books they have added to their bookshelf, behavior tags can be added to the books corresponding to the historical behavior data based on historical behavior data. The behavior tags include read tags and / or bookshelf tags. Those skilled in the art can set the specific tagging format of the behavior tags according to actual needs, and this is not limited here.

[0058] Specifically, the "read" mark is used to identify books that have been read by the user but not added to the bookshelf, while the "on bookshelf" mark is used to identify books that have been added to the bookshelf. If the user's historical behavior data for a book indicates that the user has read the book but has not added it to the bookshelf, the "read" mark is added to the book; if the user's historical behavior data for a book indicates that the user has added the book to the bookshelf, the "on bookshelf" mark is added to the book.

[0059] Step S210: Displaying the processed book information and action mark of each book in the list on the book list page.

[0060] When a user enters a book list page, the processed book information of each book in the list and the behavior mark of each book may be displayed on the book list page. Figure 2d Shows the display of the book list page Figure 1 ,like Figure 2d As shown, the book list page shows a list of books of different publication types arranged in descending order of popularity. In the book list page, a book card area 21 with multiple books is displayed. In the book card area 21 of each book, the book information of the book is displayed. The book information includes the book cover, title, and book description text, where "X" represents a character. For books that the user has read but not added to the bookshelf, a read mark 22 is displayed in the upper right corner of the book card area 21, that is, Figure 2d For books that the user has added to the bookshelf, a bookshelf mark 23 is displayed in the upper right corner of the book card area 21, that is, Figure 2d Markup in the form of "On Bookshelf" text is shown.

[0061] Optionally, the book list page can also provide a function to block books on the list that the user has read but not added to the bookshelf. A read block switch component can be set at a preset position on the book list page. Those skilled in the art can adjust the preset position according to actual needs. The user can turn the block function on or off by triggering the read block switch component.

[0062] Specifically, in response to a user's request to activate the read block switch component on the book list page, the user's read books are removed from the books on the processed list displayed on the book list page. The read books here may specifically include books that the user has read but not added to the bookshelf. Those skilled in the art may also configure the read books to include books that the user has read and added to the bookshelf, etc., which is not limited here.

[0063] That is, only the user's unread books can be displayed on the book list page, without displaying the user's read books, so that the user can quickly filter out unread books from the list for browsing. In addition, if the user has turned on the blocking function, the blocking function can be turned off by triggering the read blocking switch component again. Specifically, in response to the user's request to turn off the read blocking switch component on the book list page, the display of the user's read books on the book list page is restored, that is, the book information of each book in the processed list is displayed on the book list page, wherein the displayed books include the user's unread books and read books.

[0064] like Figure 2d As shown, a read shielding switch component 24 is set at the upper right corner of the book list page. The user can turn on or off the shielding function by triggering the read shielding switch component 24. If the user turns on the shielding function by triggering the read shielding switch component 24, the updated book list page can be as follows Figure 2e As shown in the figure, the books marked as read are removed from the list displayed on the book list page, that is, book 1 is removed, and the book information of more books is displayed in the order of the books in the list. Figure 2e If the read shielding switch component 24 is triggered continuously in the page state shown, the shielding function will be turned off and the book list page will be restored to Figure 2d The page status shown.

[0065] By using the list processing method provided in this embodiment, the user's historical behavior data on books is introduced into the list sorting mechanism, and multi-level feedback nodes are set on the user's behavior path for books according to the depth of the behavior path. The user's negative feedback level data on the book is determined by analyzing the behavior path depth of the historical behavior data. For multiple books with the same initial ranking index of the list, the recommendation weight of the book corresponding to the negative feedback level data is lowered, so that the higher the level of the negative feedback level data, the lower the recommendation weight of the corresponding book. In this way, books that the user is not interested in are arranged at the back according to the recommendation weight, so that the arrangement order of the books in the list can well integrate the user's preferences, which helps to obtain better book recommendation effects; and, behavior tags can also be added to the books based on the historical behavior data, so that the user can quickly and easily identify which books on the book list page are books that they have read but not added to the bookshelf, and which books are books that they have added to the bookshelf; in addition, a read shielding function is provided to filter out read books on the list for users, which greatly facilitates users to find unread books.

[0066] Example 3

[0067] A third embodiment of the present invention provides a non-volatile storage medium, wherein the storage medium stores at least one executable instruction, and the executable instruction can execute the list processing method in any of the above method embodiments.

[0068] The executable instructions can specifically be used to enable the processor to perform the following operations: collect historical behavior data of users for books in the list to be processed; analyze the behavioral path depth of the historical behavior data to obtain the negative feedback level data of users for the books; and adjust the arrangement order of the books in the list to be processed based on the negative feedback level data to obtain the processed list.

[0069] In an optional implementation, the historical behavior data includes: book exposure behavior data, book click behavior data, book reading behavior data, and book adding behavior data.

[0070] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: set multi-level feedback nodes on the user's behavior path for the book according to the behavior path depth; analyze the behavior path depth of the historical behavior data to obtain the feedback node corresponding to the behavior path depth, and use the node data of the feedback node as the user's negative feedback level data for the book.

[0071] In an optional embodiment, the multi-level feedback nodes include: feedback nodes corresponding to books being exposed but not clicked, feedback nodes corresponding to books being clicked but not read, and feedback nodes corresponding to books being read but not added to the bookshelf.

[0072] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: collect the initial ranking index of each book in the list to be processed; determine whether the initial ranking index of any two books in the list to be processed is the same; if so, lower the recommendation weight of the book corresponding to the negative feedback level data based on the negative feedback level data, and adjust the arrangement order of any two books in the list to be processed according to the recommendation weight; if not, determine the arrangement order of any two books in the list to be processed according to the preset order of the initial ranking index.

[0073] In an optional implementation, the initial ranking indicators of the list include: book popularity, number of readers, number of book likes, number of book collections, book ratings, update time, author attention parameters and / or cumulative reading time.

[0074] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: adding behavior tags to books based on historical behavior data; wherein the behavior tags include read tags and / or bookshelf tags; and displaying the book information and behavior tags of each book in the processed list on the book list page.

[0075] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: in response to the user turning on the read shielding switch component in the book list page, remove the user's read books from each book in the processed list displayed on the book list page.

[0076] Example 4

[0077] Figure 3 A schematic structural diagram of a computing device according to a fourth embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0078] like Figure 3 As shown, the computing device may include: a processor 302 , a communications interface 304 , a memory 306 , and a communication bus 308 .

[0079] in:

[0080] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via a communication bus 308 .

[0081] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0082] The processor 302 is configured to execute the program 310, and specifically to execute the relevant steps in the above-mentioned list processing method embodiment.

[0083] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0084] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in a computing device may be processors of the same type, such as one or more CPUs, or processors of different types, such as one or more CPUs and one or more ASICs.

[0085] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0086] Program 310 can specifically be used to enable processor 302 to perform the following operations: collect historical behavior data of users for books in the list to be processed; analyze the behavioral path depth of the historical behavior data to obtain negative feedback level data of users for books; and adjust the arrangement order of books in the list to be processed based on the negative feedback level data to obtain a processed list.

[0087] In an optional implementation, the historical behavior data includes: book exposure behavior data, book click behavior data, book reading behavior data, and book adding behavior data.

[0088] In an optional embodiment, the program 310 further causes the processor 302 to perform the following operations: setting multi-level feedback nodes on the user's behavior path for books according to the behavior path depth; analyzing the behavior path depth of historical behavior data to obtain feedback nodes corresponding to the behavior path depth, and using the node data of the feedback nodes as the user's negative feedback level data for the book.

[0089] In an optional embodiment, the multi-level feedback nodes include: feedback nodes corresponding to books being exposed but not clicked, feedback nodes corresponding to books being clicked but not read, and feedback nodes corresponding to books being read but not added to the bookshelf.

[0090] In an optional embodiment, the program 310 further causes the processor 302 to perform the following operations: collect the initial ranking index of each book in the list to be processed; determine whether the initial ranking index of any two books in the list to be processed is the same; if so, lower the recommendation weight of the book corresponding to the negative feedback level data based on the negative feedback level data, and adjust the arrangement order of any two books in the list to be processed according to the recommendation weight; if not, determine the arrangement order of any two books in the list to be processed according to the preset order of the initial ranking index.

[0091] In an optional implementation, the initial ranking indicators of the list include: book popularity, number of readers, number of book likes, number of book collections, book ratings, update time, author attention parameters and / or cumulative reading time.

[0092] In an optional embodiment, the program 310 further causes the processor 302 to perform the following operations: adding behavior tags to books based on historical behavior data; wherein the behavior tags include read tags and / or bookshelf tags; and displaying the book information and behavior tags of each book in the processed list on the book list page.

[0093] In an optional embodiment, the program 310 further causes the processor 302 to perform the following operations: in response to the user turning on the read shielding switch component in the book list page, remove the user's read books from each book in the processed list displayed on the book list page.

[0094] The specific implementation of each step in program 310 can be found in the description of the corresponding steps in the above-mentioned list processing embodiment, and will not be repeated here. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process description in the above-mentioned method embodiment, and will not be repeated here.

[0095] Through the solution provided in this embodiment, the user's negative feedback level data for books is determined by analyzing the behavioral path depth of historical behavioral data, and the order of books in the list is adjusted according to the negative feedback level data, thereby effectively adjusting the order of books that the user is not interested in, so that the user's preferences can be integrated to determine the order of books in the list.

[0096] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general-purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0097] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0098] Similarly, it should be understood that in order to streamline the present disclosure and aid understanding of one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims that follow the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the invention.

[0099] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0100] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0101] It should be noted that the above embodiments illustrate rather than limit the present invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A list processing method, comprising: Collect historical behavior data of users on books on the pending list; Setting up multi-level feedback nodes on the user's book behavior path according to the depth of the behavior path; wherein the multi-level feedback nodes include: feedback nodes corresponding to exposure to books but not clicking on them, feedback nodes corresponding to clicking on books but not reading them, and feedback nodes corresponding to reading books but not adding them to the bookshelf; Analyze the behavioral path depth of the historical behavioral data to obtain a feedback node corresponding to the behavioral path depth, and use the node data of the feedback node as the user's negative feedback level data for the book; wherein the node data of the feedback node includes the level of the feedback node; under the premise that the book has not been added to the bookshelf, the deeper the behavioral path depth, the higher the possibility that the user is not interested in the book, and the higher the level of the corresponding feedback node; the higher the level of the negative feedback level data, the lower the recommendation weight; According to the negative feedback level data, the order of the books in the to-be-processed list is adjusted to obtain a processed list.

2. The method according to claim 1, wherein the historical behavior data comprises: Book exposure behavior data, book click behavior data, book reading behavior data, and book adding behavior data.

3. The method according to claim 1, wherein adjusting the order of the books in the list to be processed based on the negative feedback level data to obtain the processed list further comprises: Collecting the initial ranking index of each book in the list to be processed; Determine whether the initial ranking indexes of any two books in the list to be processed are the same; If so, lowering the recommendation weight of the book corresponding to the negative feedback level data according to the negative feedback level data, and adjusting the order of the two books in the list to be processed according to the recommendation weight; If not, the order of arrangement of the two books in the to-be-processed list is determined according to the preset order of the initial sorting index of the list.

4. According to the method of claim 3, the initial ranking index of the list includes: Book popularity, number of readers, number of book likes, number of book collections, book ratings, update time, author follow parameters and / or cumulative reading time.

5. The method according to any one of claims 1 to 4, further comprising: Adding behavior marks to the books based on the historical behavior data; wherein the behavior marks include read marks and / or bookshelf marks; The book list page displays the book information of each book in the processed list and the behavior mark of each book.

6. The method according to any one of claims 1 to 4, further comprising: In response to a user turning on a read shielding switch component in a book list page, books read by the user are removed from each book in a processed list displayed on the book list page.

7. A computing device comprising: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations: Collect historical behavior data of users on books on the pending list; Setting up multi-level feedback nodes on the user's book behavior path according to the depth of the behavior path; wherein the multi-level feedback nodes include: feedback nodes corresponding to exposure to books but not clicking on them, feedback nodes corresponding to clicking on books but not reading them, and feedback nodes corresponding to reading books but not adding them to the bookshelf; Analyze the behavioral path depth of the historical behavioral data to obtain a feedback node corresponding to the behavioral path depth, and use the node data of the feedback node as the user's negative feedback level data for the book; wherein the node data of the feedback node includes the level of the feedback node; under the premise that the book has not been added to the bookshelf, the deeper the behavioral path depth, the higher the possibility that the user is not interested in the book, and the higher the level of the corresponding feedback node; the higher the level of the negative feedback level data, the lower the recommendation weight; According to the negative feedback level data, the order of the books in the to-be-processed list is adjusted to obtain a processed list.

8. The computing device according to claim 7, wherein the historical behavior data comprises: Book exposure behavior data, book click behavior data, book reading behavior data, and book adding behavior data.

9. The computing device of claim 7, wherein the executable instructions further cause the processor to: Collecting the initial ranking index of each book in the list to be processed; Determine whether the initial ranking indexes of any two books in the list to be processed are the same; If so, lowering the recommendation weight of the book corresponding to the negative feedback level data according to the negative feedback level data, and adjusting the order of the two books in the list to be processed according to the recommendation weight; If not, the order of arrangement of the two books in the to-be-processed list is determined according to the preset order of the initial sorting index of the list.

10. The computing device according to claim 9, wherein the initial ranking index of the list comprises: Book popularity, number of readers, number of book likes, number of book collections, book ratings, update time, author follow parameters and / or cumulative reading time.

11. The computing device according to any one of claims 7 to 10, wherein the executable instructions further cause the processor to perform the following operations: Adding behavior tags to the books based on the historical behavior data; wherein, The behavior mark includes a read mark and / or a bookshelf mark; The book list page displays the book information of each book in the processed list and the behavior mark of each book.

12. The computing device according to any one of claims 7 to 10, wherein the executable instructions further cause the processor to perform the following operations: In response to a user turning on a read shielding switch component in a book list page, books read by the user are removed from each book in a processed list displayed on the book list page.

13. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and wherein the executable instruction causes a processor to execute an operation corresponding to the list processing method according to any one of claims 1 to 6.

Images